← All stories
● Covered by 1 source · 1 reportMedium impact1 neutral

Google releases PARDIG and SatWeave datasets for AI weather modeling

🔄 Updated 8d ago
New to BrevFeed? We gather this story from every outlet covering it into one summary — ranked by real-world impact, not just the latest headline — so you never miss what matters. What is BrevFeed? →

Key points

  • PARDIG and SatWeave datasets are now publicly available.
  • Datasets were foundational for Google's WeatherNext 3 model.
  • SatWeave unifies imagery from five geostationary satellites.
  • PARDIG is an AI-based global precipitation dataset.

New Datasets for Weather Prediction

Google has made two foundational datasets, PARDIG and SatWeave, publicly available. These datasets are intended to assist researchers and developers in creating new applications related to weather, hydrology, and climate. Both datasets were integral to the development of Google's recently released WeatherNext 3 model.

SatWeave: Unified Satellite Imagery

SatWeave provides a global mosaic of geostationary satellite imagery. It integrates data from five different satellites: GOES-East, GOES-West, Meteosat 0, Meteosat Indian Ocean, and Himawari. This unification addresses challenges posed by varying map projections, file formats, sensors, and scan schedules (10 to 30 minutes) across individual satellite feeds. Existing global composites often reduce channel count or update frequency to manage these incompatibilities.

PARDIG: AI-Based Precipitation Data

PARDIG is an AI-based global precipitation dataset. This dataset was specifically used to train the precipitation forecast capabilities of the WeatherNext 3 model. Both PARDIG and SatWeave are available with historical archives and live feeds, allowing researchers to use them in their own modeling and downstream applications.

Impact on Research and Development

The release of these datasets aims to support the global community in advancing the understanding and prediction of Earth's weather and water cycle. Converting raw satellite and ground instrument measurements into coherent, rapidly available global pictures is a significant scientific and engineering challenge, which these datasets are designed to help address.

✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →

The daily brief

One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.

One email a day. Unsubscribe in one click, any time.

Today's brief

Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.

~4 min · 3 stories · Nov 21

▶ Play today's brief Listen on Spotify

New every morning, and the back catalogue is archived by date.

Primary sources

arXiv 2611.13941

Reporting from

Google has released two datasets, PARDIG and SatWeave, which were used in its WeatherNext 3 model. These datasets provide global precipitation data and unified geostationary satellite imagery, respectively, to support research and development in weather, hydrology, and climate applications.